Posterior Uncertainty Quantification in Neural Networks using Data Augmentation

arXiv:2403.12729v1 Announce Type: cross
Abstract: In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen future data. Under this view, we show that deep ensembling (Lakshminarayanan et al., 2017) is a fundamentally mis-specified model class, since it assumes that future data are supported on existing observations only -- a situation rarely encountered in practice. To address this …

abstract arxiv assumptions augmentation cs.lg data deep learning distribution framework future networks neural networks paper parameters posterior predictive quantification show stat.ml through type uncertainty view